Opus 4.5 is not the normal AI agent experience that I have had thus far • Hacker News Board

Re: Opus 4.5 is not the normal AI agent experience that I have had thus far

#681

Post by rat9988 » Wed, Jan 07, 2026, 12:53 PM UTC

bayindirh wrote: post #677

redhale wrote: post #673

Earlier quoted context omitted.

Not necessarily responding to you directly, but I find this take to be interesting, and I see it every time an article like this makes the rounds. Starting back in 2022/2023: - (~2022) It can auto-complete one line, but it can't write a full function. - (~2023) Ok, it can write a full function, but it can't write a full feature. - (~2024) Ok, it can write a full feature, but it can't write a simple application. - (~2…

Well, the first 90% is easy, the hard part is the second 90%. Case in point: Self driving cars. Also, consider that we need to pirate the whole internet to be able to do this, so these models are not creative. They are just directed blenders.

> Well, the first 90% is easy, the hard part is the second 90%.

You'd need to prove that this assertion applies here. I understand that you can't deduce the future gains rate from the past, but you also can't state this as universal truth.

Re: Opus 4.5 is not the normal AI agent experience that I have had thus far

#682

Post by edg5000 » Wed, Jan 07, 2026, 12:55 PM UTC

adriand wrote: post #53

ChrisbyMe wrote: post #6

Mm this is my experience as well, but I'm not particularly worried about software engineering a whole. If anything this example shows that these cli tools give regular devs much higher leverage. There's a lot of software labor that is like, go to the lowest cost country, hire some mediocre people there and then hire some US guy to manage them. That's the biggest target of this stuff, because now that US guy can just…

> If anything this example shows that these cli tools give regular devs much higher leverage. This is also my take. When the printing press came out, I bet there were scribes who thought, "holy shit, there goes my job!" But I bet there were other scribes who thought, "holy shit, I don't have to do this by hand any more?!" It's one thing when something like weaving or farming gets automated. We have a finite need for…

The mechanization and scaling up of farming caused a tectonic shift from rural residents moving to cities to take on factory jobs as well as office and retail jobs. We saw this in China until very recently, since they had a bit of a slow start causing delayed full-scale industrialisation.

So a lot of people will end up doing something different. Some of it will be menial and be shit, and some of it will be high level. New hierarchies and industries will form. Hard to predict the details, but history gives us good parallels.

Re: Opus 4.5 is not the normal AI agent experience that I have had thus far

#683

Post by pmg101 » Wed, Jan 07, 2026, 12:56 PM UTC

mmkos wrote: post #634

hollowturtle wrote: post #626

Earlier quoted context omitted.

I don't buy the huge impact, should already have happened and didn't actually happened by now. The day I'll see all these ai hypers producing products that will replace current gen/old gen products like Windows, Excel etc I will buy it, for now it's just hype and ai dooming

I see societal changes like container ships turning. Society has a massive cultural momentum so of course not much has changed today, but we'll have seen big changes years from now. The tools are only just getting really good at what they do.

The problem is that this is unfalsifiable. I could equally say that any recent events has caused a chain of events leading to anything I dream up ... But we won't see the effects yet. It's a nonsense hypothesis since it can't be falsified.

Re: Opus 4.5 is not the normal AI agent experience that I have had thus far

#684

Post by edg5000 » Wed, Jan 07, 2026, 12:58 PM UTC

kachapopopow wrote: post #19

It's also the feeling I have, opus is not a ground-breaking model by any means. However, Opus 4.5 is incredible when you give it everything it needs, a direction, what you have versus what you want and it will make it work, really, it will work. The code might me ugly, undesirable, would only work for that one condition, but with futher prompting you can evolve it and produce something that you can be proud of. Opus…

Opus can produce beatiful code. It can outcode a good programmer. But getting it to do this reliably is something I've gotten better at over the last year; it's a skill that took quite a bit of practice.

I now write very long specifications and this helps. I haven't figured out a bulletproof workflow, I think that will take years. But I often get just amazing code out of it.

Re: Opus 4.5 is not the normal AI agent experience that I have had thus far

#685

Post by sanderjd » Wed, Jan 07, 2026, 1:05 PM UTC

redhale wrote: post #673

multisport wrote: post #320

What bothers me about posts like this is: mid-level engineers are not tasked with atomic, greenfield projects. If all an engineer did all day was build apps from scratch, with no expectation that others may come along and extend, build on top of, or depend on, then sure, Opus 4.5 could replace them. The hard thing about engineering is not "building a thing that works", its building it the right way, in an easily unde…

Not necessarily responding to you directly, but I find this take to be interesting, and I see it every time an article like this makes the rounds. Starting back in 2022/2023: - (~2022) It can auto-complete one line, but it can't write a full function. - (~2023) Ok, it can write a full function, but it can't write a full feature. - (~2024) Ok, it can write a full feature, but it can't write a simple application. - (~2…

Yeah maybe, but personally it feels more like a plateau to me than an exponential takeoff, at the moment.

And this isn't a pessimistic take! I love this period of time where the models themselves are unbelievably useful, and people are also focusing on the user experience of using those amazing models to do useful things. It's an exciting time!

But I'm still pretty skeptical of "these things are about to not require human operators in the loop at all!".

Re: Opus 4.5 is not the normal AI agent experience that I have had thus far

#686

Post by sanderjd » Wed, Jan 07, 2026, 1:07 PM UTC

rat9988 wrote: post #681

bayindirh wrote: post #677

Earlier quoted context omitted.

Well, the first 90% is easy, the hard part is the second 90%. Case in point: Self driving cars. Also, consider that we need to pirate the whole internet to be able to do this, so these models are not creative. They are just directed blenders.

> Well, the first 90% is easy, the hard part is the second 90%. You'd need to prove that this assertion applies here. I understand that you can't deduce the future gains rate from the past, but you also can't state this as universal truth.

I read the comment more as "based on past experience, it is usually the case that the first 90% is easier than the last 10%", which is the right base case expectation, I think. That doesn't mean it will definitely play out that way, but you don't have to "prove" things like this. You can just say that they tend to be true, so it's a good expectation to think it will probably be true again.

Re: Opus 4.5 is not the normal AI agent experience that I have had thus far

#687

Post by throwthrowuknow » Wed, Jan 07, 2026, 1:09 PM UTC

sanderjd wrote: post #685

redhale wrote: post #673

Earlier quoted context omitted.

Not necessarily responding to you directly, but I find this take to be interesting, and I see it every time an article like this makes the rounds. Starting back in 2022/2023: - (~2022) It can auto-complete one line, but it can't write a full function. - (~2023) Ok, it can write a full function, but it can't write a full feature. - (~2024) Ok, it can write a full feature, but it can't write a simple application. - (~2…

Yeah maybe, but personally it feels more like a plateau to me than an exponential takeoff, at the moment. And this isn't a pessimistic take! I love this period of time where the models themselves are unbelievably useful, and people are also focusing on the user experience of using those amazing models to do useful things. It's an exciting time! But I'm still pretty skeptical of "these things are about to not require…

I can agree that it doesn’t seem exponential yet but this is at least linear progression not a plateau.

Re: Opus 4.5 is not the normal AI agent experience that I have had thus far

#688

Post by throwthrowuknow » Wed, Jan 07, 2026, 1:14 PM UTC

bayindirh wrote: post #677

redhale wrote: post #673

Earlier quoted context omitted.

Not necessarily responding to you directly, but I find this take to be interesting, and I see it every time an article like this makes the rounds. Starting back in 2022/2023: - (~2022) It can auto-complete one line, but it can't write a full function. - (~2023) Ok, it can write a full function, but it can't write a full feature. - (~2024) Ok, it can write a full feature, but it can't write a simple application. - (~2…

Well, the first 90% is easy, the hard part is the second 90%. Case in point: Self driving cars. Also, consider that we need to pirate the whole internet to be able to do this, so these models are not creative. They are just directed blenders.

Even if Opus 4.5 is the limit it’s still a massively useful tool. I don’t believe it’s the limit though for the simple fact that a lot could be done by creating more specialized models for each subdomain i.e. they’ve focused mostly on web based development but could do the same for any other paradigm.

Re: Opus 4.5 is not the normal AI agent experience that I have had thus far

#689

Post by arkensaw » Wed, Jan 07, 2026, 1:15 PM UTC

redhale wrote: post #673

multisport wrote: post #320

What bothers me about posts like this is: mid-level engineers are not tasked with atomic, greenfield projects. If all an engineer did all day was build apps from scratch, with no expectation that others may come along and extend, build on top of, or depend on, then sure, Opus 4.5 could replace them. The hard thing about engineering is not "building a thing that works", its building it the right way, in an easily unde…

Not necessarily responding to you directly, but I find this take to be interesting, and I see it every time an article like this makes the rounds. Starting back in 2022/2023: - (~2022) It can auto-complete one line, but it can't write a full function. - (~2023) Ok, it can write a full function, but it can't write a full feature. - (~2024) Ok, it can write a full feature, but it can't write a simple application. - (~2…

> It's pretty clear to me where this is going. The only question is how long it takes to get there.

I don't think its a guarantee. all of the things it can do from that list are greenfield, they just have increasing complexity. The problem comes because even in agentic mode, these models do not (and I would argue, can not) understand code or how it works, they just see patterns and generate a plausible sounding explanation or solution. agentic mode means they can try/fail/try/fail/try/fail until something works, but without understanding the code, especially of a large, complex, long-lived codebase, they can unwittingly break something without realising - just like an intern or newbie on the project, which is the most common analogy for LLMs, with good reason.

Re: Opus 4.5 is not the normal AI agent experience that I have had thus far

#690

Post by ikornaselur » Wed, Jan 07, 2026, 1:16 PM UTC

theshrike79 wrote: post #339

spaceman_2020 wrote: post #54

Earlier quoted context omitted.

I really think a lof of people tried AI coding earlier, got frustrated at the errors and gave up. That's where the rejection of all these doomer predictions comes from. And I get it. Coding with Claude Code really was prompting something, getting errors, and asking it to fix it. Which was still useful but I could see why a skilled coder adding a feature to a complex codebase would just give up Opus 4.5 really is at a…

> "asking it to fix it." This is what people are still doing wrong. Tools in a loop people, tools in a loop. The agent has to have the tools to detect whatever it just created is producing errors during linting/testing/running. When it can do that, I can loop again, fix the error and again - use the tools to see whether it worked. I _still_ encounter people who think "AI programming" is pasting stuff into ChatGPT on…

Last weekend I was debugging some blocking issue on a microcontroller with embassy-rs, where the whole microcontroller would lock up as soon as I started trying to connect to an MQTT server.

I was having Opus investigate it and I kept building and deploying the firmware for testing.. then I just figured I'd explain how it could do the same and pull the logs.

Off it went, for the next ~15 minutes it would flash the firmware multiple times until it figured out the issue and fixed it.

There was something so interesting about seeing a microcontroller on the desk being flashed by Claude Code, with LEDs blinking indicating failure states. There's something about it not being just code on your laptop that felt so interesting to me.

But I agree, absolutely, red/green test or have a way of validating (linting, testing, whatever it is) and explain the end-to-end loop, then the agent is able to work much faster without being blocked by you multiple times along the way.